Here are the steps to obtain the schema for SQL generation using LinkAlign:
- Preprocess the data:
python preprocess.py --base_dir ./spider2_dev
- Generate the schemas:
python generate_schemas.py \
--save_path ./spider2_dev/instance_schemas \
--schema_path ./spider2_dev/schemas \
--dataset ./spider2_dev/spider2_dev_preprocessed.json \
--db_info_path ./spider2_dev/db_info.json \
--external_info_path ./spider2_dev/external_knowledge
By the way, you can leverage components from tools/SchemaLinkingTool.py (like in generate_schemas.py) to build more effective schema linking pipelines.
Originally posted by @Satissss in #6
1. when execute the step 2 "Generate the schemas" got below exceptions, how to fix it?
0%| | 1/411 [00:01<12:28, 1.82s/it][Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/ga360/vector_store/docstore.json' [Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/ga360/vector_store/docstore.json' 1%| | 3/411 [00:03<06:41, 1.02it/s][Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/ga360/vector_store/docstore.json' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS_GOOGLE' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS_GOOGLE' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS_GOOGLE' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' 4%|▍ | 17/411 [00:03<00:47, 8.26it/s][Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/ga4/vector_store/docstore.json' [Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/ga360/vector_store/docstore.json' [Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/PATENTSVIEW/vector_store/docstore.json' 5%|▌ | 21/411 [00:04<01:07, 5.79it/s][Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/PATENTSVIEW/vector_store/docstore.json' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\GITHUB_REPOS' [Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/PATENTS_USPTO/vector_store/docstore.json' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\GITHUB_REPOS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\GITHUB_REPOS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\GITHUB_REPOS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\GITHUB_REPOS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PYPI' 7%|▋ | 28/411 [00:05<00:41, 9.17it/s][Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/PATENTSVIEW/vector_store/docstore.json' 'VectorIndexRetriever' object has no attribute 'index'
2. and where to get or how to generate these files: "db_info.json " "spider2_dev_preprocessed.json" "tables_preprocessed.json" files?
Originally posted by @Satissss in #6
1. when execute the step 2 "Generate the schemas" got below exceptions, how to fix it?
0%| | 1/411 [00:01<12:28, 1.82s/it][Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/ga360/vector_store/docstore.json' [Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/ga360/vector_store/docstore.json' 1%| | 3/411 [00:03<06:41, 1.02it/s][Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/ga360/vector_store/docstore.json' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS_GOOGLE' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS_GOOGLE' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS_GOOGLE' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PATENTS' 4%|▍ | 17/411 [00:03<00:47, 8.26it/s][Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/ga4/vector_store/docstore.json' [Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/ga360/vector_store/docstore.json' [Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/PATENTSVIEW/vector_store/docstore.json' 5%|▌ | 21/411 [00:04<01:07, 5.79it/s][Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/PATENTSVIEW/vector_store/docstore.json' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\GITHUB_REPOS' [Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/PATENTS_USPTO/vector_store/docstore.json' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\GITHUB_REPOS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\GITHUB_REPOS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\GITHUB_REPOS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\GITHUB_REPOS' [WinError 3] 系统找不到指定的路径。: 'spider2_dev\\schemas\\PYPI' 7%|▋ | 28/411 [00:05<00:41, 9.17it/s][Errno 2] No such file or directory: '*********/LinkAlign/spider2_dev/schemas/PATENTSVIEW/vector_store/docstore.json' 'VectorIndexRetriever' object has no attribute 'index'2. and where to get or how to generate these files: "db_info.json " "spider2_dev_preprocessed.json" "tables_preprocessed.json" files?